Cloud GPUs with Spot Pricing — May 2026
GPUs available with spot/preemptible pricing — typically 50-80% cheaper than on-demand for fault-tolerant workloads.
NVIDIA
192 GB
B200
HBM3e
Blackwell
$1.99/hr
NVIDIA
141 GB
H200 SXM
HBM3e
Hopper
$2.05/hr
NVIDIA
80 GB
H100 SXM
HBM3
Hopper
$1.57/hr
NVIDIA
80 GB
A100 SXM (80GB)
HBM2e
Ampere
$1.10/hr
NVIDIA
48 GB
L40S
GDDR6
Ada Lovelace
$0.55/hr
NVIDIA
48 GB
A40
GDDR6
Ampere
$0.30/hr
NVIDIA
96 GB
RTX PRO 6000
GDDR7
Blackwell
$1.71/hr
NVIDIA
48 GB
RTX 6000 Ada
GDDR6
Ada Lovelace
$0.47/hr
NVIDIA
48 GB
RTX A6000
GDDR6
Ampere
$0.30/hr
NVIDIA
32 GB
RTX 5090
GDDR7
Blackwell
$0.34/hr
NVIDIA
24 GB
RTX 4090
GDDR6X
Ada Lovelace
$0.28/hr
NVIDIA
24 GB
RTX 3090
GDDR6X
Ampere
$0.12/hr
B200 vs H200 SXM vs H100 SXM — top picks from this guide
|
B200
Blackwell · 192 GB
|
H200 SXM
Hopper · 141 GB
|
H100 SXM
Hopper · 80 GB
|
|
|---|---|---|---|
| Specifications | |||
| Manufacturer | NVIDIA | NVIDIA | NVIDIA |
| Architecture | Blackwell | Hopper | Hopper |
| VRAM | 192 GB HBM3e | 141 GB HBM3e | 80 GB HBM3 |
| Memory Bandwidth | 8,000 GB/s | 4,800 GB/s | 3,350 GB/s |
| FP16 (Tensor) | 2,250 TFLOPS | 990 TFLOPS | 990 TFLOPS |
| FP32 | 75 TFLOPS | 67 TFLOPS | 67 TFLOPS |
| TDP | 1000 W | 700 W | 700 W |
| Release Year | 2024 | 2024 | 2023 |
| Segment | Data center | Data center | Data center |
| Cloud Pricing | |||
| Cheapest On-Demand | $1.99/hr | $2.05/hr | $1.57/hr |
| Providers | 2 | 3 | 7 |
Build your own GPU comparison
Select any 2 GPUs from this guide and open them side-by-side.
Tip: GPU comparisons run in pairs. Pick exactly 2 — if you skip selection, we open the top 2 from this guide.